{"list":"other","total":65,"rows":[{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2207.01206","title":"WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents","created":"2022-07-04","cited_by_count":1251},{"id":"1809.08887","title":"Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task","created":"2018-09-24","cited_by_count":1139},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688},{"id":"1709.00103","title":"Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning","created":"2017-08-31","cited_by_count":687},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"2304.11015","title":"DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction","created":"2023-04-21","cited_by_count":477},{"id":"1911.04942","title":"RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers","created":"2019-11-10","cited_by_count":424},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"id":"2308.15363","title":"Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation","created":"2023-08-29","cited_by_count":385},{"id":"2309.10691","title":"MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback","created":"2023-09-19","cited_by_count":297},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243},{"id":"2306.14898","title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","created":"2023-06-26","cited_by_count":238},{"id":"2411.07763","title":"Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows","created":"2024-11-12","cited_by_count":232},{"id":"2402.16347","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","created":"2024-02-26","cited_by_count":187},{"id":"1909.05378","title":"CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases","created":"2019-09-11","cited_by_count":185},{"id":"2405.16755","title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","created":"2024-05-27","cited_by_count":169},{"id":"2312.11242","title":"MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL","created":"2023-12-18","cited_by_count":164},{"id":"1906.02285","title":"SParC: Cross-Domain Semantic Parsing in Context","created":"2019-06-05","cited_by_count":144},{"id":"2410.01943","title":"CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL","created":"2024-10-02","cited_by_count":138},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124},{"id":"2503.15478","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","created":"2025-03-19","cited_by_count":118},{"id":"2106.11455","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","created":"2021-06-22","cited_by_count":106},{"id":"2405.07467","title":"MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation","created":"2024-05-13","cited_by_count":105},{"id":"2301.07507","title":"Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing","created":"2023-01-18","cited_by_count":93},{"id":"2503.02240","title":"OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale","created":"2025-03-04","cited_by_count":91},{"id":"2212.09248","title":"Natural Language to Code Generation in Interactive Data Science Notebooks","created":"2022-12-19","cited_by_count":87},{"id":"2407.15186","title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","created":"2024-07-21","cited_by_count":67},{"id":"2408.07702","title":"The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models","created":"2024-08-14","cited_by_count":67},{"id":"2503.23157","title":"Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL","created":"2025-03-29","cited_by_count":59},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57},{"id":"2411.00073","title":"RSL-SQL: Robust Schema Linking in Text-to-SQL Generation","created":"2024-10-31","cited_by_count":52},{"id":"2405.15307","title":"Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation","created":"2024-05-24","cited_by_count":50},{"id":"2402.01117","title":"DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models","created":"2024-02-02","cited_by_count":45},{"id":"2106.05006","title":"Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data","created":"2021-06-09","cited_by_count":43},{"id":"2507.04701","title":"XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL","created":"2025-07-07","cited_by_count":40},{"id":"2404.00405","title":"A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration","created":"2024-03-30","cited_by_count":38},{"id":"2309.06275","title":"Re-Reading Improves Reasoning in Large Language Models","created":"2023-09-12","cited_by_count":37},{"id":"2406.19073","title":"AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries","created":"2024-06-27","cited_by_count":35},{"id":"2409.16751","title":"E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL","created":"2024-09-25","cited_by_count":35},{"id":"2310.13659","title":"Benchmarking and Improving Text-to-SQL Generation under Ambiguity","created":"2023-10-20","cited_by_count":34},{"id":"2502.17248","title":"Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search","created":"2025-02-24","cited_by_count":34},{"id":"2506.13752","title":"Steering LLM Thinking with Budget Guidance","created":"2025-06-16","cited_by_count":33},{"id":"2308.11534","title":"PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulator","created":"2023-08-21","cited_by_count":29},{"id":"2508.17196","title":"BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens","created":"2025-08-24","cited_by_count":29},{"id":"2503.16431","title":"OpenAI's Approach to External Red Teaming for AI Models and Systems","created":"2025-01-24","cited_by_count":28},{"id":"2410.11076","title":"PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries","created":"2024-10-14","cited_by_count":19},{"id":"2301.01067","title":"Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge","created":"2023-01-03","cited_by_count":18},{"id":"2403.05307","title":"Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents","created":"2024-03-08","cited_by_count":17},{"id":"2409.08330","title":"Real or Robotic? Assessing Whether LLMs Accurately Simulate Qualities of Human Responses in Dialogue","created":"2024-09-12","cited_by_count":16},{"id":"2506.00391","title":"SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL","created":"2025-05-31","cited_by_count":16},{"id":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","cited_by_count":16},{"id":"2502.01523","title":"CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering","created":"2025-02-03","cited_by_count":15},{"id":"2310.18742","title":"Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL","created":"2023-10-28","cited_by_count":11},{"id":"2411.09972","title":"Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems","created":"2024-11-15","cited_by_count":11},{"id":"2507.20439","title":"When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions","created":"2025-07-27","cited_by_count":11},{"id":"2508.15276","title":"AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL","created":"2025-08-21","cited_by_count":11},{"id":"2507.22478","title":"SLM-SQL: An Exploration of Small Language Models for Text-to-SQL","created":"2025-07-30","cited_by_count":10},{"id":"2502.12257","title":"InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Context","created":"2025-02-17","cited_by_count":8}],"next_cursor":null}